Havuz

Introducing Muse Glimmer: open-weight 30B agentic multimodal model that runs on your device (Meta). Interactive local agent lab + guide. Apa

甲作 Atelier：手机端 AI 美甲推荐与虚拟试戴；仓库公开其中的轻量评测工作台。

Open-source, customizable frontend for Venice AI. Chat, image gen, audio, video, embeddings + visual workflows — all in one UI. Your API key

Free unlimited Gemini API for any OpenAI-compatible app.

Local-first visual media plugin for DeepSeek Harness: local video preprocessing, native vision, copyable image history, and video playback.

Search knowledge by what documents mean and how they look — not one or the other.

NAS OS

An open-source, self-hosted social AI agent across QQ, Telegram, Feishu/Lark and personal clients, with persistent identity, long-term memor

Beyond Time Shifts (ECCV 2026): a reference-free audio-visual synchronization evaluator built on Qwen2.5-Omni-3B, with SynthSync data, R-GRP

MODA: open fashion retrieval benchmark and models by Hopit AI. MODA (203M, open source), MODA Pro Lite (213M, open weights), MODA Pro (hoste

OpenCode vision support: automatically saves pasted images and guides non-vision models to recognize them via tool calling. Supports single

Local NotebookLM for Claude Code via Google Antigravity (agy / Gemini 3.x): /agy:notebook turns a folder of documents into per-doc summaries

Use your X Premium or SuperGrok subscription in pi.

Codex Skill：让纯文本模型（DeepSeek）借助 StepFun step-3.7-flash 获得看图能力 | Give text-only Codex models (DeepSeek) image understanding via StepFun step-3

Aster describes what a lecture video shows but never says, so blind and low-vision students can follow it

Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator

A unified Model Context Protocol server for MiniMax CLI (mmx)

A multimodal RAG dashboard and interactive 3D Knowledge Graph. Process documents locally with Ollama or via Cloud APIs, powered by LightRAG,

小红书图文笔记 Agent Skill，支持看图理解、主动提问、智能选题、实时热梗搜索、标题正文、标签评论钩子和风险检查。

Multimodal AI studio powered by Qwen3.6-35B-A3B. End-to-end web app exposing visual reasoning, image captioning, and document understanding

Android 16 fork. AI as a platform primitive. Twelve capabilities, one shared runtime, every app. OEM-pluggable. Apache 2.0.

A beautiful Gemini-powered chat interface with multimodal support

Long-term memory infrastructure for .NET AI agents with semantic, temporal, spatial and robotics memory, hybrid retrieval, and pluggable pro

macOS computer-use agent in the notch. Long-press, talk, Claude drives the mouse.

Capability-aware vision + paste extension for the pi coding agent. Delegates image analysis only when the active model is text-only; passes

Cognitive-structured Multimodal Agent (CMA-Harness): a memory-centric agent for long-horizon multimodal understanding, generation, and editi

Give non-multimodal Claude Code main models the ability to see pasted screenshots — a ~200-line UserPromptSubmit hook.

Generate editable scientific SVG figures from method text with local SAM3 and dual-provider routing.

Multimodal document QA: vision + retrieval over PDFs (LLaVA + LlamaIndex)